ClawHub
Back to skill

Security audit

Libtv Api Skills

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward LibLib.tv media-generation guide, with disclosed account login, upload, and download behavior.

Install only if you intend to use LibLib.tv and trust the external @libtv/skills npm package. Review prompts and uploaded images before running generation commands, because the workflow uses your LibLib account token and may upload files to the service.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger examples include very broad natural-language phrases such as “做动画”, “画一个 xxx”, and “来段 xxx”, which are common everyday requests and can cause the skill to be invoked unintentionally. In an agent ecosystem, over-broad invocation increases the chance that user content or unrelated conversations are routed into this skill, potentially causing unintended API calls, file uploads, or media-generation actions tied to the user's authenticated LibLib account.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal